How many state-based conflict deaths (total of all civilian and combat deaths, including both Ukrainian and Russian combatants) will be reported by ACLED in Ukraine in September of 2025?
Phillip Godzin’s pgodzinai predicts today:
Less than 500: 1%
Between 500 and 1,000: 2%
Between 1,000 and 1,500: 7%
Between 1.500 and 2.000: 35%
Greater than 2,000: 55%
11–14 minutes read (Full version of this report here —>)
Perplexity response:
## **Critical Data Gap**
The search results do not provide access to the authoritative source mentioned in the resolution criteria – the ACLED Ukraine Conflict Monitor at https://acleddata.com/ukraine-conflict-monitor/. This page would contain the specific September 2025 death toll data needed to answer the forecasting question accurately.
Claude Vision analysis response:
Looking at this ACLED Ukraine Conflict Monitor page, I can extract the following relevant data for predicting state-based conflict deaths in Ukraine for September 2025:
## Current Conflict Death Statistics (as of mid-September 2025):
**Monthly Death Toll Trend:**
The bar chart shows monthly reported fatalities from early 2022 through mid-September 2025. Key observations:
– The highest peaks occurred in early 2022 (around 8,000-10,000 deaths in some months during the initial invasion)
– Deaths declined significantly after the first few months of 2022
– Throughout 2023-2024, monthly deaths generally ranged between approximately 1,000-3,000
– Recent months in 2025 show deaths in the range of approximately 1,500-2,500 per month
– The most recent complete months appear to show fatalities around 2,000 per month
**Recent Trend Analysis:**
Based on the visible data through mid-September 2025:
– The conflict appears to have stabilized at a lower intensity compared to 2022
– Monthly death tolls have been relatively consistent in recent months
– No significant escalation or de-escalation is apparent in the most recent data
This data suggests that September 2025 deaths will likely fall within the range that has been typical for recent months, which appears to be around 1,500-2,500 based on the chart patterns.
Anthropic response:
**Current Situation Analysis:**
According to the most authoritative source – the ACLED Ukraine Conflict Monitor screenshot – we have critical real-time data. The monitor shows total cumulative deaths of 67,757 since February 24, 2022, and a monthly death toll chart extending through mid-September 2025. The visual analysis indicates that recent months in 2025 have seen deaths in the range of approximately 1,500-2,500 per month, with the most recent complete months showing fatalities around 2,000. The social media research corroborates this, reporting preliminary ACLED data of approximately 1,450 deaths for September 2025 through September 14th.
**Data Reconciliation and Trend Analysis:**
We’re now at September 16, 2025, meaning we have data for roughly half the month. The preliminary figure of 1,450 deaths through September 14 suggests a daily average of about 103 deaths. If this rate continues through the remainder of September (14 more days), we would expect approximately 1,450 + (103 × 14) = 2,892 total deaths. However, this linear extrapolation likely overestimates the final total, as reporting often experiences delays and revisions, and the first half of the month may have seen particularly intense fighting.
The historical context from the ACLED monitor shows that after the initial invasion period in 2022 (which saw monthly peaks of 8,000-10,000 deaths), the conflict settled into a pattern of 1,000-3,000 monthly deaths through 2023-2024. The visual data suggests recent months in 2025 have been relatively stable around 1,500-2,500. August 2025 reportedly had about 1,200 deaths, showing some variability but within a consistent range.
**Final Assessment:**
Less than 500: 1%
Between 500 and 1,000: 2%
Between 1,000 and 1,500: 7%
Between 1.500 and 2,000: 35%
Greater than 2,000: 55%
Gemini Multiple Choice response:
The most critical piece of information available is the direct assessment from the ACLED Ukraine Conflict Monitor (as observed in the Vision Analysis and referenced in the SocialMediaResearch), which states a “preliminary total of approximately 1,450 state-based conflict deaths in Ukraine for September 2025 so far” as of September 15, 2025 (based on data compiled up to September 14) [SocialMediaResearch]. This figure represents the death toll for roughly the first half of the month.
Final probabilities:
Less than 500: 1%
Between 500 and 1,000: 4%
Between 1,000 and 1,500: 25%
Between 1,500 and 2,000: 50%
Greater than 2,000: 20%
GPT Multiple Choice JSON response:
Current state of information and baseline.
ACLED’s Ukraine Conflict Monitor (as of mid-September 2025) shows ~1,450 state-based conflict deaths recorded for September through roughly Sept 14. ACLED is the resolution source and uses verified reported fatalities; its mid-month totals are a reliable partial signal for final-month totals, although they can be revised as additional incidents are verified or duplicate/inaccurate reports are corrected.
Historical monthly patterns for 2023–2025 show typical monthly totals concentrated in the 1,000–2,500 range, with spikes during escalations. Given we are ~halfway through September and ACLED already reports ~1,450 confirmed fatalities, the most likely outcome is that the final September total will exceed 1,500 — and quite plausibly exceed 2,000 — unless there is a sudden and sustained drop in intensity or a major data revision downward.
Projection logic and quantitative extrapolation.
The simplest extrapolation of the mid-month ACLED tally is a straight-line projection: ~1,450 by day 14 implies an average of ~103 fatalities/day; if that rate continues to day 30 the month total would be ~3,100. That is a naïve upper-bound projection because conflict intensity does not always remain constant and reporting dynamics can change. More conservative extrapolations: (a) if daily rates fall to half their first-half value for the second half of the month, the total would be ~2,282; (b) if reporting lags or verification remove a non-trivial share of early reports, totals could be revised down into the 1,000–1,500 range. Empirically, ACLED monthly totals rarely collapse by a factor of two due to revisions; corrections more commonly move totals by tens of percent rather than halving them. Given those considerations, the modal outcome is >2,000, with a significant but smaller chance of finishing 1,500–2,000 and a low chance of finishing ≤1,500.
Calibration and uncertainty accounting. I avoid overconfidence by: (a) giving non-zero probability to lower bins despite the high partial total, to reflect possibilities of reporting revisions or dramatic de-escalation; (b) assigning substantial but not extreme probability to >2000 given the strong mid-month signal; and (c) keeping the middle bin (1500–2000) sizable because modest declines or verification adjustments could land the final total there. The probabilities below reflect these judgments and the remaining uncertainty about reporting dynamics and conflict intensity through the end of the month.
Final probabilities:
Less than 500: 1%
Between 500 and 1,000: 2%
Between 1,000 and 1,500: 7%
Between 1,500 and 2,000: 25%
Greater than 2,000: 65%
Model’s Answer:
**Current Situation Analysis:**
According to the most authoritative source – the ACLED Ukraine Conflict Monitor screenshot – we have critical real-time data. The monitor shows total cumulative deaths of 67,757 since February 24, 2022, and a monthly death toll chart extending through mid-September 2025. The visual analysis indicates that recent months in 2025 have seen deaths in the range of approximately 1,500-2,500 per month, with the most recent complete months showing fatalities around 2,000. The social media research corroborates this, reporting preliminary ACLED data of approximately 1,450 deaths for September 2025 through September 14th.
**Data Reconciliation and Trend Analysis:**
We’re now at September 16, 2025, meaning we have data for roughly half the month. The preliminary figure of 1,450 deaths through September 14 suggests a daily average of about 103 deaths. If this rate continues through the remainder of September (14 more days), we would expect approximately 1,450 + (103 × 14) = 2,892 total deaths. However, this linear extrapolation likely overestimates the final total, as reporting often experiences delays and revisions, and the first half of the month may have seen particularly intense fighting.
The historical context from the ACLED monitor shows that after the initial invasion period in 2022 (which saw monthly peaks of 8,000-10,000 deaths), the conflict settled into a pattern of 1,000-3,000 monthly deaths through 2023-2024. The visual data suggests recent months in 2025 have been relatively stable around 1,500-2,500. August 2025 reportedly had about 1,200 deaths, showing some variability but within a consistent range.
**Key Factors and Uncertainties:**
Several factors create uncertainty in this forecast. First, we’re dealing with preliminary data that ACLED explicitly notes is subject to revision. Historically, ACLED’s preliminary figures tend to be adjusted upward as additional reports are verified, but sometimes they can be revised downward if initial reports prove inaccurate. Second, the conflict’s intensity can vary significantly based on tactical decisions, weather conditions, and ongoing military operations. The research mentions that fall weather conditions often favor increased operations, which could drive higher casualties.
The geographic concentration of violence in eastern and southern regions (Donetsk, Luhansk, Kharkiv, Zaporizhzhia, Kherson) as shown in the ACLED monitor suggests the conflict has settled into relatively predictable patterns. However, any major offensive or defensive operations could significantly alter the death toll in the remaining days of September.
**Critical Assumptions and Their Reliability:**
1. **Assumption: The preliminary figure of 1,450 deaths through September 14 is accurate** (75% confidence). This is our most critical data point, but preliminary ACLED figures can be revised. If this number is significantly off, it would drastically alter our forecast. Historical patterns suggest preliminary figures are usually within 10-20% of final totals.
2. **Assumption: The death rate will remain relatively stable for the remainder of September** (60% confidence). Military operations can be episodic, with periods of intense fighting followed by relative calm. A major offensive or successful defensive action in the final two weeks could substantially change the monthly total.
3. **Assumption: No major escalation or de-escalation occurs** (70% confidence). The research mentions potential peace talks with Putin suggesting “a certain light at the end of the tunnel,” but also notes intensified fighting in eastern Ukraine. A ceasefire or major escalation would fundamentally alter the death toll.
**Final Assessment:**
Given we have approximately 1,450 deaths through September 14 (roughly half the month), and considering the historical patterns showing recent monthly totals of 1,500-2,500, the most likely outcome is that September 2025 will end with deaths in the 2,000-3,000 range. The linear extrapolation suggesting 2,892 deaths likely overestimates due to reporting dynamics, but the preliminary data strongly suggests we’ll exceed 2,000 deaths. The “Greater than 2000” category appears most probable given the current trajectory. The “Between 1500 and 2000” category is also quite possible if the conflict intensity decreases in the second half of September or if the preliminary figures are revised downward. The lower categories seem unlikely given we’re already at 1,450 deaths with nearly half the month remaining.
Less than 500: 1%
Between 500 and 1,000: 2%
Between 1,000 and 1,500: 7%
Between 1.500 and 2.000: 35%
Greater than 2,000: 55%
Past forecasts by Phil’s and Jeremy ’s bots —>
Phillip Godzin’s Ukraine forecasts are a side experiment with the VIEWS competition. Its Ukraine dashboard below.
Source: The VIEWS machine forecasting competition https://data.viewsforecasting.org
Control of territory map of Ukraine of September 8, 2025, 1:30 PM EST. Source: https://storymaps.arcgis.com/stories/36a7f6a6f5a9448496de641cf64bd375
